News for hackers. Stuff that matters.
Re:Llama.cpp: Full CUDA GPU Acceleration by jiggawatts on Tuesday June 13, 2023 @12:12AM (#36305184)
I wonder if it would be possible to emulate/translate CUDA to target non-NVIDIA hardware.

I suspect it would be more of a legal challenge than a technical one.

Re:Llama.cpp: Full CUDA GPU Acceleration by mahkeiro on Tuesday June 13, 2023 @01:18AM (#36305757)
That's what ROCm was trying to do